{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XEHXHXHA5TC4NBKASBYERFVABV","short_pith_number":"pith:XEHXHXHA","schema_version":"1.0","canonical_sha256":"b90f73dce0ecc5c6854090704896a00d794a8caa9a8ca70fd78d21c60ff82f15","source":{"kind":"arxiv","id":"2408.15496","version":4},"attestation_state":"computed","paper":{"title":"ReMamba: Equip Mamba with Effective Long-Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bei Li, Danlong Yuan, Dongyan Zhao, Huishuai Zhang, Jiahao Liu, Jingang Wang, Xunliang Cai","submitted_at":"2024-08-28T02:47:27Z","abstract_excerpt":"While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited compared to transformer-based models. In this study, we investigate the long-context efficiency issues of the Mamba models and propose ReMamba, which enhances Mamba's ability to comprehend long contexts. ReMamba incorporates selective compression and adaptation techniques within a two-stage re-forward process, incurring minimal additional inference costs overh"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2408.15496","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T02:47:27Z","cross_cats_sorted":[],"title_canon_sha256":"55f424f6e75f6547862ad3b40e0b33b82c232f0f9cb052a015e9336c7e5d2879","abstract_canon_sha256":"8314efee5b9d4928380d0b0a8ba1c1cbd2beb946eade20452684160fd10981f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:59.864711Z","signature_b64":"ZBX+2b1jNpCD6V7RALfwJU1byds3zorE9tb/9Uri2ZYjwfY22LgWt46M6u4QOyUsneJQH57jz6FtdcRMXPK5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b90f73dce0ecc5c6854090704896a00d794a8caa9a8ca70fd78d21c60ff82f15","last_reissued_at":"2026-07-05T09:55:59.864235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:59.864235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReMamba: Equip Mamba with Effective Long-Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bei Li, Danlong Yuan, Dongyan Zhao, Huishuai Zhang, Jiahao Liu, Jingang Wang, Xunliang Cai","submitted_at":"2024-08-28T02:47:27Z","abstract_excerpt":"While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited compared to transformer-based models. In this study, we investigate the long-context efficiency issues of the Mamba models and propose ReMamba, which enhances Mamba's ability to comprehend long contexts. ReMamba incorporates selective compression and adaptation techniques within a two-stage re-forward process, incurring minimal additional inference costs overh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15496","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.15496/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.15496","created_at":"2026-07-05T09:55:59.864293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15496v4","created_at":"2026-07-05T09:55:59.864293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15496","created_at":"2026-07-05T09:55:59.864293+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEHXHXHA5TC4","created_at":"2026-07-05T09:55:59.864293+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEHXHXHA5TC4NBKA","created_at":"2026-07-05T09:55:59.864293+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEHXHXHA","created_at":"2026-07-05T09:55:59.864293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16424","citing_title":"Safety, Security, and Cognitive Risks in State-Space Models: A Systematic Threat Analysis with Spectral, Stateful, and Capacity Attacks","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEHXHXHA5TC4NBKASBYERFVABV","json":"https://pith.science/pith/XEHXHXHA5TC4NBKASBYERFVABV.json","graph_json":"https://pith.science/api/pith-number/XEHXHXHA5TC4NBKASBYERFVABV/graph.json","events_json":"https://pith.science/api/pith-number/XEHXHXHA5TC4NBKASBYERFVABV/events.json","paper":"https://pith.science/paper/XEHXHXHA"},"agent_actions":{"view_html":"https://pith.science/pith/XEHXHXHA5TC4NBKASBYERFVABV","download_json":"https://pith.science/pith/XEHXHXHA5TC4NBKASBYERFVABV.json","view_paper":"https://pith.science/paper/XEHXHXHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15496&json=true","fetch_graph":"https://pith.science/api/pith-number/XEHXHXHA5TC4NBKASBYERFVABV/graph.json","fetch_events":"https://pith.science/api/pith-number/XEHXHXHA5TC4NBKASBYERFVABV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEHXHXHA5TC4NBKASBYERFVABV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEHXHXHA5TC4NBKASBYERFVABV/action/storage_attestation","attest_author":"https://pith.science/pith/XEHXHXHA5TC4NBKASBYERFVABV/action/author_attestation","sign_citation":"https://pith.science/pith/XEHXHXHA5TC4NBKASBYERFVABV/action/citation_signature","submit_replication":"https://pith.science/pith/XEHXHXHA5TC4NBKASBYERFVABV/action/replication_record"}},"created_at":"2026-07-05T09:55:59.864293+00:00","updated_at":"2026-07-05T09:55:59.864293+00:00"}